CoolFace
Modelpublic

lainlives/codegemma-7b-it-bnb-4bit

sourceHugging Faceapache-2.0updated 6mo agoView on Hugging Face
0likes13downloads
config.json49 linesDownload Raw Back to root
1{2  "architectures": [3    "GemmaModel"4  ],5  "attention_bias": false,6  "attention_dropout": 0.0,7  "bos_token_id": 2,8  "dtype": "bfloat16",9  "eos_token_id": 1,10  "head_dim": 256,11  "hidden_act": "gelu_pytorch_tanh",12  "hidden_activation": "gelu_pytorch_tanh",13  "hidden_size": 3072,14  "initializer_range": 0.02,15  "intermediate_size": 24576,16  "max_position_embeddings": 8192,17  "model_type": "gemma",18  "num_attention_heads": 16,19  "num_hidden_layers": 28,20  "num_key_value_heads": 16,21  "pad_token_id": 0,22  "quantization_config": {23    "_load_in_4bit": true,24    "_load_in_8bit": false,25    "bnb_4bit_compute_dtype": "bfloat16",26    "bnb_4bit_quant_storage": "uint8",27    "bnb_4bit_quant_type": "nf4",28    "bnb_4bit_use_double_quant": true,29    "llm_int8_enable_fp32_cpu_offload": false,30    "llm_int8_has_fp16_weight": false,31    "llm_int8_skip_modules": null,32    "llm_int8_threshold": 6.0,33    "load_in_4bit": true,34    "load_in_8bit": false,35    "quant_method": "bitsandbytes"36  },37  "rms_norm_eps": 1e-06,38  "rope_parameters": {39    "rope_theta": 10000.0,40    "rope_type": "default"41  },42  "tie_word_embeddings": true,43  "transformers_version": "5.3.0.dev0",44  "unsloth_version": "2024.9",45  "use_bidirectional_attention": null,46  "use_cache": true,47  "vocab_size": 25600048}49